Hengduo Li
11 papers · 2018–2024 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (29) π Conference Polyglot (4) π Academic Marathon (6) π Interdisciplinary Bridge π§ Keyword Pioneer
π
Interdisciplinary Bridge
π§
Keyword Pioneer
π§¬
Topic Evolution
β
The Questioner
ποΈ
Keyword Collector
(50)
π₯
Unstoppable
(5)
π
Century Club
(11)
Conferences
CVPR (6)
ECCV (3)
AAAI (1)
ICML (1)
Top co-authors
Keywords
convolutional neural network
(3)
object detection
(3)
adaptive computation
(2)
video understanding
(2)
policy gradient
(1)
conditional computation
(1)
semi-supervised learning
(1)
multimodal learning
(1)
object recognition
(1)
text generation
(1)
pseudo labeling
(1)
fine-grained classification
(1)
class imbalance
(1)
efficient inference
(1)
efficient computing
(1)
video recognition
(1)
label noise
(1)
feature space
(1)
vision transformer
(1)
reinforcement learning
(1)
Papers
Object Recognition as Next Token Prediction
CVPR 2024
SEGIC: Unleashing the Emergent Correspondence for In-Context Segmentation
ECCV 2024
MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding
CVPR 2024
Rethinking Pseudo Labels for Semi-supervised Object Detection
AAAI 2022
AdaViT: Adaptive Vision Transformers for Efficient Image Recognition
CVPR 2022
Semi-Supervised Single-View 3D Reconstruction via Prototype Shape Priors
ECCV 2022
Efficient Video Transformers with Spatial-Temporal Token Selection
ECCV 2022
2D or not 2D? Adaptive 3D Convolution Selection for Efficient Video Recognition
CVPR 2021
Learning From Noisy Anchors for One-Stage Object Detection
CVPR 2020
Transferable Clean-Label Poisoning Attacks on Deep Neural Nets
ICML 2019
R-FCN-3000 at 30fps: Decoupling Detection and Classification
CVPR 2018